Information Extraction Conflict Arbitration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing information extraction methods from natural language texts often produce conflicting results due to differences in extraction techniques, leading to inefficiencies and reduced quality in identifying and classifying information objects.
Innovation Solution
A system and method that apply multiple information extraction techniques to natural language texts, identify sets of conflicting objects, and utilize a conflict arbitration function to modify, delete, or merge objects based on morphological, lexical, syntactic, and semantic attributes to produce a final list of extracted information objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple information extraction techniques are applied to natural language texts, then the quantity of extracted information objects increases, but the number of conflicting information objects also increases
Solution Approach 1:
The patent segments the information extraction process into multiple independent techniques (e.g., rule-based extraction, machine learning-based extraction, pattern matching) that operate in parallel. Each technique extracts information objects independently, and their results are then combined and reconciled through conflict resolution mechanisms, allowing the system to leverage the strengths of each technique while managing conflicts systematically
Solution Approach 2:
The patent introduces an intermediary conflict resolution module that mediates between multiple extraction techniques. This module receives conflicting information objects from different techniques, applies resolution rules and algorithms to identify and resolve conflicts, and produces a unified set of extracted information objects, thereby maintaining reliability while utilizing multiple extraction approaches
2Measurement precision
If multiple information extraction techniques are applied to natural language texts, then the precision of information extraction improves, but the computational complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-processing the natural language text (e.g., tokenization, lemmatization, stopword removal) before applying multiple extraction techniques. It also pre-defines extraction rules, patterns, and conflict resolution strategies in advance, reducing the computational burden during the actual extraction and conflict resolution phases, thereby maintaining high precision while managing computational complexity
Solution Approach 2:
The patent merges multiple information extraction techniques and their results into a unified processing framework. By combining the strengths of different techniques (rule-based, machine learning, pattern matching) and integrating their outputs through conflict resolution, the system achieves higher precision without requiring separate independent processing pipelines, thus optimizing computational efficiency
3Manufacturing precision
If conflict arbitration functions are applied to resolve conflicting information objects, then the quality of final extracted information improves, but the processing time increases
Solution Approach 1:
The patent changes parameters of the conflict arbitration process by adjusting resolution rules, confidence thresholds, and priority weights based on the specific characteristics of conflicting information objects. This allows the system to adaptively resolve conflicts with appropriate scrutiny levels, improving quality while avoiding excessive processing time for low-risk conflicts
Solution Approach 2:
The patent applies partial conflict resolution by focusing arbitration efforts on conflicting objects that meet specific criteria (e.g., high confidence conflicts, semantically significant conflicts) rather than applying exhaustive resolution to all conflicts. This selective approach maintains high quality for critical extractions while reducing overall processing time
Data Source
AI summary
Systems and methods for extracting facts from natural language texts. An example method of information extraction comprises extracting, from a natural language text, a first plurality of information objects; extracting, from the natural language text, a second plurality of information objects; identifying a set of conflicting information objects, such that a first information object of the set of conflicting information objects belongs to the first plurality of information objects and a second information object of the set of conflicting information objects belongs to the second plurality of information objects; and producing a final list of information objects extracted from the natural language text, by applying, to the set of conflicting information objects, a conflict arbitration function which performs at least one of: modifying the first information object, deleting the first information object, or merging two or more information objects of the set of conflicting information objects.